Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances where a specific action needs to be taken in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when" to identify conditional scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agin
    -0.86
    rolet
    -0.73
    alin
    -0.72
    Lay
    -0.72
    gur
    -0.70
    aido
    -0.67
    him
    -0.66
    hole
    -0.66
    edly
    -0.65
    andal
    -0.65
    POSITIVE LOGITS
    soever
    1.39
     applying
    0.81
     confronted
    0.80
     encountering
    0.80
    abouts
    0.77
     comparing
    0.77
     evaluating
    0.77
     applied
    0.76
     viewed
    0.76
     traveling
    0.75
    Act Density 0.126%

    No Known Activations